GPT-5.6 Luna

OpenAI GPT-5.6 Luna — efficient GPT-5.6 model for cost-sensitive, high-volume workloads.

GPT-5.6 Luna is available through AnyFast via the OpenAI Responses API (/v1/responses). According to OpenAI’s official model guidance, gpt-5.6-luna is optimized for cost-sensitive, high-volume workloads within the GPT-5.6 family.

Use gpt-5.6-luna when throughput and cost efficiency matter more than maximum model capability.

Key capabilities

• Responses API — Uses the newer /v1/responses endpoint with input instead of messages
• Efficient tier — GPT-5.6 model optimized for cost-sensitive, high-volume workloads
• Long context — Supports a 1.05M token context window and up to 128K output tokens
• Advanced reasoning — Supports reasoning effort levels: none, low, medium (default), high, xhigh, and max
• Pro mode — Set reasoning.mode to pro for quality-first requests that can tolerate higher latency and token use
• Persisted reasoning — Use reasoning.context to control whether prior reasoning is reused across turns
• Verbosity control — Set response verbosity to low, medium, or high
• Streaming — Supports real-time token streaming via SSE
• Tool use — Supports function calling, web search, file search, code interpreter, computer use, and other Responses API tools
• Programmatic Tool Calling — Supports bounded tool-heavy workflows where the model can write JavaScript to coordinate eligible tools

Quick example

cURL

curl https://www.anyfast.ai/v1/responses \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.6-luna",
    "input": [
      { "role": "user", "content": "Explain quantum entanglement in simple terms." }
    ],
    "reasoning": {
      "effort": "high",
      "summary": "auto",
      "context": "auto"
    },
    "text": {
      "format": { "type": "text" },
      "verbosity": "medium"
    },
    "store": true
  }'

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://www.anyfast.ai/v1"
)

response = client.responses.create(
    model="gpt-5.6-luna",
    input=[
        {"role": "user", "content": "Explain quantum entanglement in simple terms."}
    ],
    reasoning={"effort": "high", "summary": "auto", "context": "auto"},
    text={"format": {"type": "text"}, "verbosity": "medium"},
    store=True
)

print(response.output[0].content[0].text)

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://www.anyfast.ai/v1"
)

stream = client.responses.create(
    model="gpt-5.6-luna",
    input=[
        {"role": "user", "content": "Write a short poem about the sea."}
    ],
    stream=True
)

for event in stream:
    if hasattr(event, 'delta'):
        print(event.delta, end="")

Parameters

Parameter	Type	Required	Description
model	string	Yes	Must be gpt-5.6-luna
input	array	Yes	List of { role, content } objects
stream	boolean	No	Enable SSE streaming. Default: false
temperature	float	No	0–2. Controls randomness. Default: 1
max_output_tokens	integer	No	Maximum output tokens to generate. Minimum: 16
stop	string / array	No	Sequences that stop generation
reasoning	object	No	{ effort, summary, mode, context } — effort: none / low / medium / high / xhigh / max; mode can be pro; context can be auto, all_turns, or current_turn
text	object	No	{ format, verbosity } — controls output format and verbosity
tools	array	No	List of tools the model may call
prompt_cache_options	object	No	Configure explicit prompt caching behavior when supported
safety_identifier	string	No	Stable privacy-preserving end-user identifier for safety systems
store	boolean	No	Store response for later retrieval. Default: true

API Reference

View the interactive API playground for GPT-5.6 Luna.